We propose a Dynamic Graph-Based Spatial-Temporal Attention (DG-STA) method for hand
gesture recognition. The key idea is to first construct a fully-connected graph from a hand …

Action recognition methods are disclosed. An embodiment of the methods includes:
identifying a video that comprises images of a human body to be processed; identifying at …

Automatic deformable 3D modeling is computationally expensive, especially when
considering complex position, orientation and scale variations. We present a volume …

Machine learning has been advanced considerably by the development of deep learning.
Conventional deep-learning techniques are, however, limited to topologically regular data …

Very recent advances in machine learning have expanded deep learning methods to
spatially-irregular data domains. Deep learning on graphs in particular has received greater …